Skip to content

MiaoDX/roboclaws / skills/household-world

household-world

Verified

Complete household-world goals through public household MCP tools.

FileKindSize
SKILL.mdskill md12.6 KB
scripts/scratchpad.pyexecutablescript5.6 KB
scripts/target_query_recovery.pyscript1.5 KB
scripts/trace_preserving_cleanup.pyexecutablescript4.9 KB
skill.jsonconfig2.9 KB

skill.json

View on GitHub
{
  "schema": "roboclaws_skill_manifest_v1",
  "name": "household-world",
  "summary": "Run household-world goals through public map, observation, episode, and optional manipulation capabilities.",
  "abstraction_level": "agent_skill",
  "role": "household_world_task_behavior",
  "status": "active",
  "mcp": {
    "profiles": ["household_world", "household_episode", "household_manipulation"],
    "required_tools": [
      "metric_map",
      "navigate_to_waypoint",
      "observe",
      "adjust_camera",
      "resolve_target_query",
      "done"
    ],
    "optional_tools": [
      "declare_visual_candidates",
      "navigate_to_visual_candidate",
      "navigate_to_object",
      "pick",
      "navigate_to_receptacle",
      "place",
      "place_inside",
      "open_receptacle",
      "close_receptacle",
      "navigate_to_room",
      "inspect_visible_object",
      "check_operator_messages"
    ],
    "privileged_tools": [],
    "boundary_notes": "Public/private-safe household surface. No scene_objects, hidden destination table, generated mess truth, target list, or private scoring truth."
  },
  "capability_requirements": {
    "profiles": ["household_world", "household_episode", "household_manipulation"],
    "backend_variants": ["api_semantic_synthetic", "molmospaces_subprocess", "agibot_gdk"],
    "notes": "GoalContract, TaskIntentSpec, TaskPresetSpec, and required capabilities decide whether manipulation is enabled. The skill name is not task-specific."
  },
  "scripts": [
    {
      "path": "scripts/trace_preserving_cleanup.py",
      "kind": "routine",
      "summary": "Reference wrapper for the canonical observed-object cleanup routine. It composes public atomic MCP tools through an injected call_tool function and preserves semantic substeps."
    },
    {
      "path": "scripts/target_query_recovery.py",
      "kind": "artifact_review",
      "summary": "Offline helper for inspecting public runtime_metric_map target candidates. It is not permission to read private manifests or simulator inventory."
    },
    {
      "path": "scripts/scratchpad.py",
      "kind": "scratchpad",
      "summary": "Non-authoritative run-local strategy scratchpad helpers for intent, retries, and routine summaries."
    }
  ],
  "evidence_outputs": [
    "trace.jsonl",
    "run_result.json",
    "report.html",
    "agent_view.json",
    "goal_contract.json",
    "runtime_metric_map.json"
  ],
  "lifecycle": {
    "refactor_signals": [
      "repeated household traces reveal reusable room-sweep, search, or manipulation behavior",
      "planner-backed manipulation evidence becomes common enough to split into a capability-profile subskill"
    ],
    "promote_to_mcp_when": [
      "a subproblem is stable across household intents",
      "it uses only public contract data",
      "trace and report artifacts preserve the semantic substeps",
      "live performance evidence shows skill-side composition is not good enough for cross-client use"
    ]
  }
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall